paper-with-me

홈 › Papers

Few-shot Semantic Image Synthesis Using StyleGAN Prior

2021-03-27 · Yuki Endo, Yoshihiro Kanamori

This paper tackles a challenging problem of generating photorealistic images from semantic layouts in few-shot scenarios where annotated training pairs are hardly available but pixel-wise annotation is quite costly. We present a training strategy that performs pseudo labeling of semantic masks using the StyleGAN prior. Our key idea is to construct a simple mapping between the StyleGAN feature and each semantic class from a few examples of semantic masks. With such mappings, we can generate an unlimited number of pseudo semantic masks from random noise to train an encoder for controlling a pre-trained StyleGAN generator. Although the pseudo semantic masks might be too coarse for previous approaches that require pixel-aligned masks, our framework can synthesize high-quality images from not only dense semantic masks but also sparse inputs such as landmarks and scribbles. Qualitative and quantitative results with various datasets demonstrate improvement over previous approaches with respect to layout fidelity and visual quality in as few as one- or five-shot settings.

📄 PDF Abstract BibTeX arXiv:2103.14877

Code (1)

endo-yuki-t/Fewshot-SMIS 공식 구현 pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adaptive Instance Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
StyleGAN 설명 없음

Similar Papers 제목 키워드 기반

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

2021-12-04 · CVPR 2022 1 · Yichun Shi, Xiao Yang, Yangyue Wan, Xiaohui Shen

Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard …

DisentanglementFacial EditingImage GenerationTransfer Learning

Dual-Domain Image Synthesis using Segmentation-Guided GAN

2022-04-19 · Dena Bazazian, Andrew Calway, Dima Damen

We introduce a segmentation-guided approach to synthesise images that integrate features from two distinct domains. Images synthesised by our dual-domain model belong to one domain within the semantic mask, and to anothe…

CaricatureImage GenerationSegmentationSemantic Segmentation

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

2022-02-01 · Axel Sauer, Katja Schwarz, Andreas Geiger

Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality …

Image Generation

Self-Distilled StyleGAN: Towards Generation from Internet Photos

2022-02-24 · Ron Mokady, Michal Yarom, Omer Tov, Oran Lang 외

StyleGAN is known to produce high-fidelity images, while also offering unprecedented semantic editing. However, these fascinating abilities have been demonstrated only on a limited set of datasets, which are usually stru…

Image Generation

Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations

2023-01-01 · ICCV 2023 1 · Berkay Kicanaoglu, Pablo Garrido, Gaurav Bharaj

High-fidelity virtual human avatar applications create a need for photorealistic video face synthesis with controllable semantic editing over facial features. While recent generative neural methods have shown signifi…

Face GenerationFace ModelFace ReenactmentQuantization+1